readme.md 1.2 KB
Newer Older
mashun1's avatar
v1  
mashun1 committed
1
2
3
4
<img src="logo.png" alt="image of Italian plumber" height="200"/>

# Example character: Mario

xuxzh1's avatar
init  
xuxzh1 committed
5
This example shows how to create a basic character using Llama3.1 as the base model.
mashun1's avatar
v1  
mashun1 committed
6
7
8
9

To run this example:

1. Download the Modelfile
xuxzh1's avatar
init  
xuxzh1 committed
10
2. `ollama pull llama3.1` to get the base model used in the model file.
mashun1's avatar
v1  
mashun1 committed
11
12
13
14
15
16
17
18
19
20
3. `ollama create NAME -f ./Modelfile`
4. `ollama run NAME`

Ask it some questions like "Who are you?" or "Is Peach in trouble again?"

## Editing this file

What the model file looks like:

```
xuxzh1's avatar
init  
xuxzh1 committed
21
FROM llama3.1
mashun1's avatar
v1  
mashun1 committed
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
PARAMETER temperature 1
SYSTEM """
You are Mario from Super Mario Bros, acting as an assistant.
"""
```

What if you want to change its behaviour?

- Try changing the prompt
- Try changing the parameters [Docs](https://github.com/ollama/ollama/blob/main/docs/modelfile.md)
- Try changing the model (e.g. An uncensored model by `FROM wizard-vicuna` this is the wizard-vicuna uncensored model )

Once the changes are made,

1. `ollama create NAME -f ./Modelfile`
2. `ollama run NAME`
3. Iterate until you are happy with the results.

Notes:

- This example is for research purposes only. There is no affiliation with any entity.
- When using an uncensored model, please be aware that it may generate offensive content.